API reference

Base URL

One base URL for every request, including streaming and long context.

https://api.cognitivers.com/v1        chat, embeddings, model list
https://api.cognitivers.com/health    public health probe

Paths are appended to the base URL, so a chat request goes to https://api.cognitivers.com/v1/chat/completions.

Include the /v1 in the base URL. Most clients append the path themselves, and a base URL without it produces a request to /chat/completions, which does not exist.

One URL for every request

Use the same base URL for chat, embeddings, model discovery and long context. For streaming chat completions, set stream: true in the request body. Your API key and client configuration stay the same.

What is public

Only /v1/* and /health. Everything else on those hosts, including operational endpoints, is not reachable from the internet. The health probe checks API service health, not whether a particular model can complete a request. It does not require credentials:

curl https://api.cognitivers.com/health
# Look for "status": "ok" in the JSON response.

Discovery

GET /v1/models lists the model ids your key can call. Clients that support discovery, such as GitHub Copilot in VS Code, can read this instead of hardcoding a list. See List models.